last-checkpoint/trainer_state.json

{
  "best_metric": 11.931035995483398,
  "best_model_checkpoint": "miner_id_24/checkpoint-30",
  "epoch": 0.0006607420132809144,
  "eval_steps": 5,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.202473377603048e-05,
      "eval_loss": 11.931365013122559,
      "eval_runtime": 257.5762,
      "eval_samples_per_second": 74.223,
      "eval_steps_per_second": 37.111,
      "step": 1
    },
    {
      "epoch": 6.607420132809145e-05,
      "grad_norm": 0.010707435198128223,
      "learning_rate": 0.00012,
      "loss": 11.9321,
      "step": 3
    },
    {
      "epoch": 0.00011012366888015241,
      "eval_loss": 11.931319236755371,
      "eval_runtime": 257.6143,
      "eval_samples_per_second": 74.212,
      "eval_steps_per_second": 37.106,
      "step": 5
    },
    {
      "epoch": 0.0001321484026561829,
      "grad_norm": 0.018232014030218124,
      "learning_rate": 0.0001992114701314478,
      "loss": 11.9308,
      "step": 6
    },
    {
      "epoch": 0.00019822260398427434,
      "grad_norm": 0.00781942717730999,
      "learning_rate": 0.00018763066800438636,
      "loss": 11.9317,
      "step": 9
    },
    {
      "epoch": 0.00022024733776030483,
      "eval_loss": 11.931222915649414,
      "eval_runtime": 258.7168,
      "eval_samples_per_second": 73.895,
      "eval_steps_per_second": 36.948,
      "step": 10
    },
    {
      "epoch": 0.0002642968053123658,
      "grad_norm": 0.007844880223274231,
      "learning_rate": 0.000163742398974869,
      "loss": 11.9314,
      "step": 12
    },
    {
      "epoch": 0.0003303710066404572,
      "grad_norm": 0.010503560304641724,
      "learning_rate": 0.00013090169943749476,
      "loss": 11.9316,
      "step": 15
    },
    {
      "epoch": 0.0003303710066404572,
      "eval_loss": 11.931129455566406,
      "eval_runtime": 258.176,
      "eval_samples_per_second": 74.05,
      "eval_steps_per_second": 37.025,
      "step": 15
    },
    {
      "epoch": 0.0003964452079685487,
      "grad_norm": 0.010184229351580143,
      "learning_rate": 9.372094804706867e-05,
      "loss": 11.9315,
      "step": 18
    },
    {
      "epoch": 0.00044049467552060965,
      "eval_loss": 11.931078910827637,
      "eval_runtime": 259.3667,
      "eval_samples_per_second": 73.71,
      "eval_steps_per_second": 36.855,
      "step": 20
    },
    {
      "epoch": 0.00046251940929664014,
      "grad_norm": 0.010106095112860203,
      "learning_rate": 5.7422070843492734e-05,
      "loss": 11.9302,
      "step": 21
    },
    {
      "epoch": 0.0005285936106247316,
      "grad_norm": 0.013225448317825794,
      "learning_rate": 2.7103137257858868e-05,
      "loss": 11.9327,
      "step": 24
    },
    {
      "epoch": 0.000550618344400762,
      "eval_loss": 11.931039810180664,
      "eval_runtime": 258.7879,
      "eval_samples_per_second": 73.875,
      "eval_steps_per_second": 36.938,
      "step": 25
    },
    {
      "epoch": 0.000594667811952823,
      "grad_norm": 0.014623328112065792,
      "learning_rate": 7.022351411174866e-06,
      "loss": 11.931,
      "step": 27
    },
    {
      "epoch": 0.0006607420132809144,
      "grad_norm": 0.0317741297185421,
      "learning_rate": 0.0,
      "loss": 11.9287,
      "step": 30
    },
    {
      "epoch": 0.0006607420132809144,
      "eval_loss": 11.931035995483398,
      "eval_runtime": 258.2272,
      "eval_samples_per_second": 74.036,
      "eval_steps_per_second": 37.018,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 13022035968.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}